Pavel Zun

Surajit Das, Pavel Zun

Bright-field microscopy, a cost-effective solution for live-cell culture, is often the only resource available, along with standard CPUs, for many low-budget labs. The inherent challenges of bright-field images -- their noisiness, low contrast, and dynamic morphology -- coupled with a lack of GPU resources and complex software interfaces, hinder the desired research output. This article presents a novel microscopy image analysis framework designed for low-budget labs equipped with a standard CPU desktop. The Python-based program enables cytometric analysis of live, unstained cells in culture through an advanced computer vision and machine learning pipeline. Crucially, the framework operates on label-free data, requiring no manually annotated training data or training phase. It is accessible via a user-friendly, cross-platform GUI that requires no programming skills, while also providing a scripting interface for programmatic control and integration by developers. The end-to-end workflow performs semantic and instance segmentation, feature extraction, analysis, evaluation, and automated report generation. Its modular architecture supports easy maintenance and flexible integration while supporting both single-image and batch processing. Validated on several unstained cell types from the public dataset of livecells, the framework demonstrates superior accuracy and reproducibility compared to contemporary tools like Cellpose and StarDist. Its competitive segmentation speed on a CPU-based platform highlights its significant potential for basic research and clinical applications -- particularly in cell transplantation for personalised medicine and muscle regeneration therapies. The access to the application is available for reproducibility

Surajit Das, Pavel Zun

Brightfield microscopy of unstained live cells is challenging due to low contrast, dynamic morphology, uneven illumination, and lack of labels. Deep learning achieved SOTA performance on stained, high-contrast images but needs large labeled datasets, expensive hardware, and fails under uneven illumination. This study presents a low-cost, lightweight, annotation-free segmentation method by introducing one-time calibration-assisted unsupervised framework adaptable across imaging modalities and image type. The framework determines background via spatial standard deviation from the local mean. Uncertain pixels are resolved using fuzzy logic, cumulative squared shift of nodal intensity, statistical features, followed by post-segmentation denoising calibration which is saved as a profile for reuse until noise pattern or object type substantially change. The program runs as a script or graphical interface for non-programmers. The method was rigorously evaluated using \textit{IoU}, \textit{F1-score}, and other metrics, with statistical significance confirmed via Wilcoxon signed-rank tests. On unstained brightfield myoblast (C2C12) images, it outperformed \textit{Cellpose 3.0} and \textit{StarDist}, improving IoU by up to 48\% (average IoU = 0.43, F1 = 0.60). In phase-contrast microscopy, it achieved a mean IoU of 0.69 and an F1-score of 0.81 on the \textit{LIVECell} dataset ($n = 3178$), with substantial expert agreement ($κ> 0.75$) confirming cross-modality robustness. Successful segmentation of laser-affected polymer surfaces further confirmed cross-domain robustness. By introducing the \textit{Homogeneous Image Plane} concept, this work provides a new theoretical foundation for training-free, annotation-free segmentation. The framework operates efficiently on CPU, avoids cell staining, and is practical for live-cell imaging and biomedical applications.

Surajit Das, Gourav Roy, Pavel Zun

Live cell culture is crucial in biomedical studies for analyzing cell properties and dynamics in vitro. This study focuses on segmenting unstained live cells imaged with bright-field microscopy. While many segmentation approaches exist for microscopic images, none consistently address the challenges of bright-field live-cell imaging with high throughput, where temporal phenotype changes, low contrast, noise, and motion-induced blur from cellular movement remain major obstacles. We developed a low-cost CNN-based pipeline incorporating comparative analysis of frozen encoders within a unified U-Net architecture enhanced with attention mechanisms, instance-aware systems, adaptive loss functions, hard instance retraining, dynamic learning rates, progressive mechanisms to mitigate overfitting, and an ensemble technique. The model was validated on a public dataset featuring diverse live cell variants, showing consistent competitiveness with state-of-the-art methods, achieving 93% test accuracy and an average F1-score of 89% (std. 0.07) on low-contrast, noisy, and blurry images. Notably, the model was trained primarily on bright-field images with limited exposure to phase- contrast microscopy (<20%), yet it generalized effectively to the phase-contrast LIVECell dataset, demonstrating modality, robustness and strong performance. This highlights its potential for real- world laboratory deployment across imaging conditions. The model requires minimal compute power and is adaptable using basic deep learning setups such as Google Colab, making it practical for training on other cell variants. Our pipeline outperforms existing methods in robustness and precision for bright-field microscopy segmentation. The code and dataset are available for reproducibility 1.

Dongwei Ye, Pavel Zun, Valeria Krzhizhanovskaya et al.

In-Stent Restenosis is a recurrence of coronary artery narrowing due to vascular injury caused by balloon dilation and stent placement. It may lead to the relapse of angina symptoms or to an acute coronary syndrome. An uncertainty quantification of a model for In-Stent Restenosis with four uncertain parameters (endothelium regeneration time, the threshold strain for smooth muscle cells bond breaking, blood flow velocity and the percentage of fenestration in the internal elastic lamina) is presented. Two quantities of interest were studied, namely the average cross-sectional area and the maximum relative area loss in a vessel. Due to the computational intensity of the model and the number of evaluations required in the uncertainty quantification, a surrogate model, based on Gaussian process regression with proper orthogonal decomposition, was developed which subsequently replaced the original In-Stent Restenosis model in the uncertainty quantification. A detailed analysis of the uncertainty propagation and sensitivity analysis is presented. Around 11% and 16% of uncertainty are observed on the average cross-sectional area and maximum relative area loss respectively, and the uncertainty estimates show that a higher fenestration mainly determines uncertainty in the neointimal growth at the initial stage of the process. On the other hand, the uncertainty in blood flow velocity and endothelium regeneration time mainly determine the uncertainty in the quantities of interest at the later, clinically relevant stages of the restenosis process. The uncertainty in the threshold strain is relatively small compared to the other uncertain parameters.